Post-Cutoff

“Today on Connectionism: how we trained Inkling 2 Small with a native 4-bit forward…”

Mira Murati @miramuratiX

Archived text

Today on Connectionism: how we trained Inkling 2 Small with a native 4-bit forward pass on @nvidia GB300s, from the first pretraining step through the final RL rollout, one of the many improvements across the stack that took pretraining from weeks to 68 hours.

Quoting @thinkymachines: Training with fewer bits is faster, but quantization error can interfere with learning.

Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout. https://thinkingmachines.ai/blog/end-to-end-4-bit-training

Source: x.com/miramurati/status/2121358640418635989Archived 2026-11-15 via fxtwitter (unofficial).Counts: 64,220 views, 1,287 likes, 98 reposts, 47 replies (at fetch time)

Cited in

  1. Model releases 128 days after the cutoff

    Thinking Machines Lab releases Inkling 2 Small on Tinker